EN

イベント

カテゴリ
日時
タイトル
報告者/場所
詳細
2024/11/27 (水)
16:45〜18:15
Fusion Learning: Combining Inferences from Diverse Data Sources
Regina Y. Liu (Rutgers, the State University of New Jersey)
第一共同研究室(4F 北側)

RLiu-short bio-112024

Abstract:
Advanced data acquisition technology nowadays has often made inferences from diverse data sources easily accessible. Fusion learning refers to fusing inferences from multiple sources or studies to make more effective overall inference. We focus on the tasks: 1) Whether/When to combine inferences? 2) How to combine inferences efficiently? 3) How to combine inference to enhance the inference for a target study? We present a general framework for nonparametric and efficient fusion learning. The main tool underlying this framework is the new notion of depth confidence distribution (depth-CD), developed by combining data depth, bootstrap and confidence distributions. We show that a depth-CD is an omnibus form of confidence regions, whose contours of level sets shrink toward the true parameter value, and thus an all-encompassing inferential tool. The approach is efficient, general and robust, and readily applies to heterogeneous studies with a broad range of complex settings. The approach is demonstrated with an aviation safety analysis application in tracking aircraft landing performance.

This is joint work with Dungang Liu (U. Cincinnati) and Minge Xie (Rutgers University).

Abstract:The Asia and Pacific region has enjoyed rapid economic and human development gains in the past three decades. Though it has benefited from demographic tailwinds, investment and productivity growth are the key to these gains. The critical role of structural transformation, that is, workers moving out of agriculture into other, higher-productivity sectors in achieving productivity growth, is often underappreciated. Movement into manufacturing in particular, helped by rapid international trade integration, has been a hallmark of the structural transformation in the region. However, services have played a bigger role across the region in the past three decades. Looking ahead, enabling continued transformation will be critical. As per capita incomes have risen, the move into services will likely become even more prominent. Ensuring a shift toward more productive services will require investment in education and training to supply the needed skills, especially to allow workers to adapt to the wave of new technologies, including AI. Continued international integration in services would be key, with an eye on boosting tradability and competition in services. In many economies, enhancing agricultural productivity will still be important for promoting transformation and growth, along with lowering barriers to workers and resources moving across sectors. Policies to raise labor force participation, especially among elderly workers and women, will be critical for mitigating the impact of population aging and decline in much of the region.

2024/11/19 (火)
10:00〜11:00
京都大学経済研究所北館N202|Room N202, North Bldg., KIER

このたび、IMF(国際通貨基金)のスタッフやエコノミスト等が京都大学に来訪し、国際的なマクロ経済政策におけるIMFの役割、業務や採用等について説明(日本語・英語)を行います。どなたでもご参加いただけます。

  •  – Introduction to IMF’s work, with a focus on Asia and the Pacific Region
     – IMF as your future workplace
  • 参加希望者は、こちらのフォームより登録の上、ご参加ください。(https://forms.gle/ms1oeCMJ4mfNrLPt6)

 

なお、同日15:00~16:30にはIMFのエコノミストによる研究発表がマクロ経済学セミナーで実施されます(於:経済研究所本館409)。そちらもぜひご参加ください。
セミナーの詳細はこちら(https://www.econ.kyoto-u.ac.jp/about/seminars/41528/)

 

後援:京都大学経済研究所、京都大学キャリアサポートセンター
公式HPはこちら(https://www.career.gakusei.kyoto-u.ac.jp/events/evnt/20241119/)

 

学内問合せ先: 京都大学経済研究所先端政策分析研究センター 谷 直起(tani.naoki.4z[at]kyoto-u.ac.jp)

2024/11/15 (金)
17:00〜18:30
社人研における地域別将来人口推計(令和5年推計)の概要
小池司朗(国立社会保障・人口問題研究所)
京都大学経済研究所本館1階 106 会議室

要旨:本報告では、国立社会保障・人口問題研究所(社人研)で実施した「日本の地域別将来推計人口(令和5年推計)」(以下、「令和5年地域推計」)の推計手法を中心として、推計結果についても多少の説明を行う。将来人口推計は、基本的には過去~現在に観察された出生・死亡・人口移動の趨勢が将来も継続するという観点で行われている。地域別将来人口推計の場合、推計の肝となるのは人口移動に関する部分であり、これまで利用可能な統計等に合わせて移動数の推計方法の改良を行ってきた。「令和5年地域推計」では、仮定設定の基準となる期間を2005~2020年の5年ごと3期間として、2020~2025年に限定して新型コロナウイルス感染拡大の影響も考慮した移動仮定の設定を行った。推計結果からは、ほぼ全域的に人口減少がいっそう進展することが見て取れるが、人口学的にみた人口減少要因はほぼ自然減となる。少子化に伴う若年人口の減少によって、地方の社会減は限定的となる一方で、推計の基準時点(2020年)における人口構造が将来人口を大きく規定することになる。

2024/11/15 (金)
15:30〜17:00
社人研における全国将来人口推計(令和5年推計)の概要
岩澤美帆(国立社会保障・人口問題研究所)
京都大学経済研究所本館1階 106 会議室

要旨:本報告では、国立社会保障・人口問題研究所(社人研)で実施した「日本の将来推計人口(令和5年推計)」の推計手法と結果について報告する。前半では、公的推計の役割と方法論(人口投影という考え方、社会経済変数との関わり)、推計時点以降の年齢別人口の推計に必要な年齢別生残率の仮定(死亡仮定)、国際人口移動数(率)の仮定、そして、0歳人口の推計に必要な女性の年齢別出生率の仮定(出生仮定)の設定方法について説明する。後半では、2020年を基準人口とし、2070年まで推計された人口および年齢構成、人口動態数、日本人、外国人別の構成、機械的に仮定条件を変えた条件付き推計の結果を示す。前回推計よりも出生率仮定は低下するものの、平均寿命が延伸し、外国人の入国超過が増加することで、人口減少の進行はわずかに緩和される見込みとなった。出生中位(死亡中位)推計にもとづけば、2070年の日本は、総人口は現在の7割に減少し、65歳以上人口はおよそ4割を占め、外国人人口割合が1割を超える社会となる。

2024/11/08 (金)
17:00〜18:30
Third-party Information Provision in Market Transactions
Balazs Szentes (The University of Hong Kong)
本館1階会議室
2024/11/08 (金)
15:00〜16:30
Niklas Engbom(New York University)
京都大学法経済学部東館 8階 リフレッシュルーム

Abstract:Exploiting variation across Swedish local labor markets between 1986 and 2018, I estimate that individuals are less likely to start new firms and switch employers in an older labor market. To account for these patterns, I propose an equilibrium theory of growth with frictional labor markets. On the one hand, workforce aging raises the level of output by increasing the share of people who have found a good match with existing production technologies. On the other hand, the higher opportunity cost of switching to new technologies discourages their introduction. The offsetting level and growth effects result in high growth through the 1990s, even though the rate at which new technologies are introduced declines monotonically since the 1970s. I estimate that it will be suppressed for the next 30 years. The lower growth rate in the older economy lowers welfare for labor market entrants, but raises the value of the high-productive jobs typically held by older individuals.

2024/11/01 (金)
15:00〜16:30
James Morley(University of Sydney)
京都大学法経済学部東館 8階 リフレッシュルーム

Abstract:Using household survey data for the U.S. and Australia, we quantify the role of taxes and transfers in providing consumption insurance against income risk. While the two countries differ substantially in their degree of tax and transfer progressivity and the extent to which it reduces the variability of disposable income, we find using a semi-structural model of income, net taxes, and consumption that the overall role of taxes and transfers in affecting the elasticity of consumption with respect to permanent income shocks is similar, with an estimated 5.4 percentage point reduction for the U.S. versus 4.8 for Australia. We interpret this result using a stylized life-cycle model with incomplete markets. Counterfactual analysis for a calibrated version of the structural model shows that, while higher progressivity increases the role of taxes in providing consumption insurance, these effects are partially mitigated by less self-insurance given higher marginal tax rates. The level of wealth relative to income also reduces the effects of progressivity on consumption insurance. Thus, higher wealth-to-income ratios in Australia can explain why, despite higher progressivity, the impact of taxes and transfers on consumption insurance is similar to the U.S.

2024/10/31 (木)
17:00〜18:30
Naoko Nishimura (Ritsumeikan University)
本館1階会議室
2024/10/30 (水)
16:45〜18:15
A unified diagnostic test for regression discontinuity designs
伏島 光毅(一橋大学)
第一共同研究室(4F 北側)

要旨: Diagnostic tests for regression discontinuity design face a size-control problem. We document a massive over-rejection of the identifying restriction among empirical studies in the top five economics journals. At least one diagnostic test was rejected for 21 out of 60 studies, whereas less than 5% of the collected 799 tests rejected the null hypotheses. In other words, more than one-third of the studies rejected at least one of their diagnostic tests, whereas their underlying identifying restrictions appear valid. Multiple testing causes this problem because the median number of tests per study was as high as 12. Therefore, we offer unified tests to overcome the size-control problem. Our procedure is based on the new joint asymptotic normality of local polynomial mean and density estimates. In simulation studies, our unified tests outperformed the Bonferroni correction.

TOP